A
Artificial Intelligence Engineer
Accelera Solutions
2 hours ago
Full-time
On-site
Charleston, South Carolina, United States
This position is full time, on site in either Charleston, SC or Washington, DC metro area. Candidates must live in either of those areas as position is full time on site. This position requires the candidate have an Active Top Secret/Sensitive Compartmented Information (TS/SCI) clearance with the ability to obtain a Counterintelligence (CI) Polygraph.
Accelera Solutions is seeking an AI Engineer to design and deploy secure AI systems thatconnect foundation models with enterprise tools, data, and services. You will build agentarchitectures, advanced retrieval capabilities, and stateful workflows that perform complex taskswhile enforcing user permissions and maintaining reliable, controlled execution.
We are looking for a hands-on engineer who understands both the capabilities of autonomousagents and the discipline required to operate them in production. Strong candidates will combineAI orchestration, and distributed systems experience with a practical approach to security,observability, and human oversight.
Key Responsibilities:
Agentic Architecture & Protocol Integration: Architect modular, interoperable agentecosystems utilizing the Model Context Protocol (MCP) to standardize connectionsbetween foundation models, external tools, and enterprise data services. Design complexstateful workflows using production orchestration frameworks (LangGraph, CrewAI,Claude Agent SDK).
Next-Gen RAG & Stateful Reasoning: Engineer advanced retrieval systems includingGraph-based RAG, Agentic Routing, and Corrective RAG (CRAG). Design memoryarchitectures that optimize context window utilization and reliably manage state acrosslong-lived, multi-turn agent sessions.
Data Governance & Entitlement Enforcement: Establish strict permission boundariesaround autonomous tool calling. Map strict data serialization schemas (JSON Schema,Protocol Buffers) directly to enterprise Access Control Lists (ACLs) and RBAC/ABACpolicies so agents only retrieve data and execute actions explicitly authorized for theinvoking end-user.
Runtime Guardrails & System Stability: Build resilient execution harnesses that preventrunaway agent loops and cascading failures. Implement idempotent tool retries, stricttoken and cost budgets, deterministic early-exit stop conditions, and seamless Human-in-the-Loop (HITL) approval gates for high-consequence actions.
Qualifications Required Qualifications:
Bachelor’s degree in Cybersecurity, Computer, Electrical, or Electronics Engineering, orMathematics with a concentration in computer science or equivalent
Orchestration & Protocols: Deep, hands-on production experience with Model ContextProtocol (MCP) server/client implementations, LangGraph, CrewAI, and the ClaudeAgent SDK. Proven ability to design custom, non-standard cognitive architectures whenoff-the-shelf patterns fall short.
Advanced Retrieval & Context: Demonstrated expertise deploying GraphRAG(knowledge graphs + vector search), dynamic query routing, and self-correcting retrievalpipelines. Deep understanding of context compression, state serialization, and sessionpersistence.
Security & Schema Mapping: Strong proficiency with JSON Schema and ProtocolBuffers (Protobuf). Proven track record of integrating identity and access management(IAM) tokens/claims into AI tool execution layers to enforce zero-trust, per-user dataentitlements.
Production Reliability: Practical engineering experience building fault-tolerantdistributed systems, including idempotency keys for external API/tool mutations, implementing early-exit stop conditions, automated budget enforcement, andasynchronous HITL state suspension/resumption.
5+ years of relevant professional experience.
Willingness to work onsite at a Government facility full time.
Active Top Secret/Sensitive Compartmented Information (TS/SCI) clearance with abilityto obtain a Counterintelligence (CI) Polygraph.
Desired Qualifications:
Master’s degree in Cybersecurity, Computer, Electrical, or Electronics Engineering, orMathematics with a concentration in computer science or equivalent
Evaluation & Observability: Experience implementing agent trajectory evaluation, step level tracing (e.g., OpenTelemetry, LangSmith, Arize Phoenix), and automated red teaming for prompt injection and privilege escalation.
High-Compliance Environments: Background deploying AI systems within high-security,regulated, or mission-critical enterprise environments where auditability and data lineageare mandatory.
Systems Programming: Proficiency in Python and TypeScript/Go for building high throughput,low-latency MCP servers and custom orchestration runtimes.
Accelera Solutions is an Equal Opportunity Employer/Veterans/Disabled.
#J-18808-Ljbffr
Accelera Solutions is seeking an AI Engineer to design and deploy secure AI systems thatconnect foundation models with enterprise tools, data, and services. You will build agentarchitectures, advanced retrieval capabilities, and stateful workflows that perform complex taskswhile enforcing user permissions and maintaining reliable, controlled execution.
We are looking for a hands-on engineer who understands both the capabilities of autonomousagents and the discipline required to operate them in production. Strong candidates will combineAI orchestration, and distributed systems experience with a practical approach to security,observability, and human oversight.
Key Responsibilities:
Agentic Architecture & Protocol Integration: Architect modular, interoperable agentecosystems utilizing the Model Context Protocol (MCP) to standardize connectionsbetween foundation models, external tools, and enterprise data services. Design complexstateful workflows using production orchestration frameworks (LangGraph, CrewAI,Claude Agent SDK).
Next-Gen RAG & Stateful Reasoning: Engineer advanced retrieval systems includingGraph-based RAG, Agentic Routing, and Corrective RAG (CRAG). Design memoryarchitectures that optimize context window utilization and reliably manage state acrosslong-lived, multi-turn agent sessions.
Data Governance & Entitlement Enforcement: Establish strict permission boundariesaround autonomous tool calling. Map strict data serialization schemas (JSON Schema,Protocol Buffers) directly to enterprise Access Control Lists (ACLs) and RBAC/ABACpolicies so agents only retrieve data and execute actions explicitly authorized for theinvoking end-user.
Runtime Guardrails & System Stability: Build resilient execution harnesses that preventrunaway agent loops and cascading failures. Implement idempotent tool retries, stricttoken and cost budgets, deterministic early-exit stop conditions, and seamless Human-in-the-Loop (HITL) approval gates for high-consequence actions.
Qualifications Required Qualifications:
Bachelor’s degree in Cybersecurity, Computer, Electrical, or Electronics Engineering, orMathematics with a concentration in computer science or equivalent
Orchestration & Protocols: Deep, hands-on production experience with Model ContextProtocol (MCP) server/client implementations, LangGraph, CrewAI, and the ClaudeAgent SDK. Proven ability to design custom, non-standard cognitive architectures whenoff-the-shelf patterns fall short.
Advanced Retrieval & Context: Demonstrated expertise deploying GraphRAG(knowledge graphs + vector search), dynamic query routing, and self-correcting retrievalpipelines. Deep understanding of context compression, state serialization, and sessionpersistence.
Security & Schema Mapping: Strong proficiency with JSON Schema and ProtocolBuffers (Protobuf). Proven track record of integrating identity and access management(IAM) tokens/claims into AI tool execution layers to enforce zero-trust, per-user dataentitlements.
Production Reliability: Practical engineering experience building fault-tolerantdistributed systems, including idempotency keys for external API/tool mutations, implementing early-exit stop conditions, automated budget enforcement, andasynchronous HITL state suspension/resumption.
5+ years of relevant professional experience.
Willingness to work onsite at a Government facility full time.
Active Top Secret/Sensitive Compartmented Information (TS/SCI) clearance with abilityto obtain a Counterintelligence (CI) Polygraph.
Desired Qualifications:
Master’s degree in Cybersecurity, Computer, Electrical, or Electronics Engineering, orMathematics with a concentration in computer science or equivalent
Evaluation & Observability: Experience implementing agent trajectory evaluation, step level tracing (e.g., OpenTelemetry, LangSmith, Arize Phoenix), and automated red teaming for prompt injection and privilege escalation.
High-Compliance Environments: Background deploying AI systems within high-security,regulated, or mission-critical enterprise environments where auditability and data lineageare mandatory.
Systems Programming: Proficiency in Python and TypeScript/Go for building high throughput,low-latency MCP servers and custom orchestration runtimes.
Accelera Solutions is an Equal Opportunity Employer/Veterans/Disabled.
#J-18808-Ljbffr