Software Engineer – GenAI / Agentic AI / Cloud Engineering
We are seeking a
Software Engineer with 5+ years of experience
to design and build
AI-driven automation platforms
that enhance internal customer engagement and streamline onboarding into enterprise cryptographic services.
This role focuses on developing Python-based, cloud-native applications leveraging Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), agentic AI workflows, and modern orchestration frameworks such as LangChain and LangGraph to automate manual analysis, understand customer intent, and intelligently guide users to the appropriate cryptographic services.
The ideal candidate has strong hands-on experience building production-grade GenAI applications, integrating AI orchestration frameworks, vector search systems, and secure cloud-native microservices in AWS environments.
Key Responsibilities
Design and develop Python-based AI applications and microservices to automate internal customer engagement, onboarding, and service triage workflows.
Build and deploy GenAI-powered solutions using LLMs, embeddings, vector databases, and Retrieval-Augmented Generation (RAG) architectures.
Design and implement agentic AI workflows using frameworks such as LangChain, LangGraph, LlamaIndex, or equivalent orchestration frameworks.
Develop intelligent assistants capable of understanding natural language requests, reasoning across enterprise knowledge, and recommending appropriate cryptographic services.
Build and maintain document ingestion pipelines, chunking strategies, embedding workflows, vector indexing, and contextual retrieval systems for enterprise knowledge access.
Implement multi-step AI orchestration pipelines, including planning, tool calling, memory/context handling, and workflow execution.
Integrate AI solutions with AWS Bedrock or equivalent foundation model platforms, including model selection, prompt optimization, and inference orchestration.
Develop and maintain cloud-native microservices using AWS services such as Lambda, ECS/EKS, API Gateway, S3, DynamoDB, and event-driven architectures.
Automate manual analysis, routing, and triage processes using a combination of AI/ML models, deterministic logic, and workflow automation.
Collaborate with product, architecture, security, and compliance teams to translate business and regulatory requirements into scalable technical solutions.
Monitor, troubleshoot, and optimize production AI workloads for latency, hallucination control, reliability, observability, and cost efficiency.
Required Skills & Experience
5+ years of professional software engineering experience in backend, cloud-native, AI/ML, or platform engineering.
Strong Python development expertise with frameworks such as FastAPI, Flask, or similar backend frameworks.
Hands-on experience building production GenAI applications, not just experimentation or POCs.
Strong experience with LangChain, LangGraph, LlamaIndex, or comparable AI orchestration frameworks.
Experience designing and implementing RAG architectures, including ingestion, chunking, embeddings, retrieval optimization, and grounding strategies.
Hands-on experience with vector databases such as Pinecone, FAISS, Redis, pgvector, OpenSearch, Weaviate, or similar.
Experience building agentic workflows, tool-calling systems, memory/context management, and autonomous decision workflows.
Solid understanding of prompt engineering, LLM behavior, hallucination mitigation, output validation, and response grounding techniques.
Experience integrating with AWS Bedrock, OpenAI APIs, Anthropic, or equivalent LLM platforms.
Strong AWS cloud experience, especially with Lambda, ECS/EKS, S3, DynamoDB, API Gateway, IAM, CloudWatch, and serverless architectures.
Experience with Docker, Kubernetes, GitHub Actions, CI/CD pipelines, and infrastructure automation (CloudFormation/CDK/Terraform).
Understanding of distributed systems, API design, event-driven architectures, and microservices.
Experience working in security-sensitive, compliance-heavy, or enterprise regulated environments preferred.
Nice to Have
Experience in cryptography, PKI, certificate management, enterprise security services, or cybersecurity platforms.
Exposure to MCP (Model Context Protocol), custom AI tool integrations, or enterprise AI agent frameworks.
Experience implementing AI observability, evaluation pipelines, or model performance monitoring.
Familiarity with secure AI governance and responsible AI practices.