Senior AI Engineer

The Senior AI Engineer role at Flex Employee Services focuses on designing, building, and scaling a production-grade Generative AI and Data Platform on AWS, with emphasis on LLM powered capabilities, vector search, graph-based knowledge systems, and governed data pipelines.

Responsibilities

• Design and operationalize LLM powered applications using retrieval augmentation (RAG), embeddings, prompt orchestration, and evaluation frameworks.
• Develop vector search solutions leveraging Amazon OpenSearch.
• Build graph-based knowledge systems with Amazon Neptune.
• Integrate AWS data stores such as ElastiCache (Redis) and DynamoDB to support AI workloads.
• Construct agentic workflows using LangGraph, AutoGen, CrewAI, or equivalent frameworks.
• Incorporate LangChain or LlamaIndex for retrieval orchestration, tool calling, and context management.
• Define standards for tool integration and context sharing following MCP style designs.
• Evaluate LLM models and retrieval strategies with a focus on latency, accuracy, cost, and context limits.
• Design and build scalable data pipelines using Databricks and Apache Spark.
• Develop data ingestion, transformation, document processing, embedding generation, and indexing pipelines.
• Ensure data quality through validation, completeness, consistency, and ongoing monitoring.
• Implement data governance, access controls, retention policies, auditability, and lineage tracking.
• Develop secure and scalable backend services and APIs with robust design principles.
• Define API standards, versioning, reliability, retry logic, circuit breakers, and idempotency.
• Build reusable platform capabilities that serve multiple teams and applications.
• Establish and manage CI/CD pipelines to support rapid development cycles.
• Deploy production systems using Docker and Kubernetes, with blue/green, canary, rollback, and feature flag strategies.
• Monitor platform reliability, observability, security, data freshness, and cost optimization.
• Define and monitor GenAI quality metrics including grounding, retrieval relevance, response consistency, latency, and cost.
• Implement prompt and version tracking, evaluation pipelines, and continuous improvement workflows.
• Ensure AI security through access controls, authentication, data protection, responsible AI guardrails, privacy, and auditability.

Requirements

• 5+ years of experience in Generative AI and LLM work including RAG, embeddings, and prompt engineering.
• Hands-on experience with AWS Cloud services such as OpenSearch, Neptune, DynamoDB, and ElastiCache/Redis.
• Strong background in vector search and retrieval systems (OpenSearch or vector databases).
• Proficiency with graph databases and knowledge graph concepts (Amazon Neptune).
• Experience with LLM frameworks such as LangChain or LlamaIndex.
• Experience with agentic AI frameworks like LangGraph, AutoGen, or CrewAI.
• Experience building data pipelines with Databricks and Apache Spark (including embedding pipelines).
• Backend/API development expertise in Python, including scalable APIs and microservices.
• Proven track record of delivering production-grade Generative AI solutions.
• Strong Python programming skills and familiarity with distributed systems, API design, and scalable backend development.
• Experience building end-to-end AI/ML platforms and lifecycle delivery.
• Education: Bachelor's or Master's degree in Computer Science, Data Science, Artificial Intelligence, or a related field.

Technologies

• LangChain, LlamaIndex
• LangGraph, AutoGen, CrewAI
• OpenSearch, Amazon Neptune, DynamoDB
• ElastiCache (Redis)
• Databricks, Apache Spark
• Python, Docker, Kubernetes

Benefits

• Dental insurance
• Health insurance
• Referral program
• Vision insurance

Preferred Skills

• Model evaluation frameworks and LLM observability tools
• AI governance and compliance frameworks
• Kubernetes and advanced MLOps practices
• Model Context Protocol (MCP) patterns
• Agent-based architectures

Domain Experience

• AI/ML Platform Engineering
• Generative AI / LLM Applications
• Data Platform / Big Data Engineering

Soft Skills

• Strong problem-solving and analytical thinking
• Ability to communicate complex AI concepts clearly
• Collaborative and cross-functional mindset
• Ownership-driven and proactive execution

Application Questions

• Are you comfortable working on W2, or should you wait for a future 1099/C2C opportunity?
• Are you willing to work on a contract basis, or should you wait for future full-time opportunities?
• Do you have at least 5 years of experience with Graph Databases (Amazon Neptune, Knowledge Graphs)?
• Do you have at least 5 years of experience with Agentic AI Frameworks (LangGraph / AutoGen / CrewAI)?
• Do you have at least 5 years of experience with Databricks and Apache Spark (data pipelines, embedding pipelines)?
• Do you have at least 5 years of experience with Backend/API Development (Python, scalable APIs, microservices)?
• Do you have at least 5 years of experience with Generative AI / LLM (RAG, embeddings, prompt engineering)?
• Do you have at least 5 years of experience with AWS Cloud (OpenSearch, Neptune, DynamoDB, ElastiCache/Redis)?
• Do you have at least 5 years of experience with Vector Search and Retrieval Systems (OpenSearch / Vector DB)?