Lead Generative AI Engineer (Agentic AI, RAG 2.0, Prompt Engineering, AWS)

Job Title: Lead Generative AI Engineer (Agentic AI, RAG 2.0, Prompt Engineering, Java, AWS)
Location: Remote / Hybrid
Job Type: Contract/Full Time
Experience: 6 + years Software Engineering/Gen AI (hands-on required)
Sponsorship is not available for this role at this time.

We are hiring a Lead Generative AI Engineer to build next-generation AI-native products using the latest advancements in LLMs, Prompt Engineering, RAG 2.0, multi-agent systems, and evaluation frameworks.

This role is ideal for engineers who have worked on real-world GenAI solutions building production-grade AI assistants, retrieval systems, autonomous agents, document intelligence pipelines, and secure AI workflows in AWS Environment.

You ll work in a fast-moving Emerging Tech environment where innovation, experimentation, and shipping production AI systems are equally valued.

Key Responsibilities

• Design and build GenAI applications with Agentic AI + RAG pipelines
• Implement advanced Prompt Engineering patterns:
• structured prompts, chain-of-thought prompting strategies, self-verification, tool prompting
• Build agent orchestration workflows:
• tool-augmented agents, planner/executor agents, multi-agent collaboration
• Implement RAG 2.0 systems:
• hybrid retrieval (keyword + dense), reranking, chunking strategies, citations/grounding
• Develop backend services using:
• Java (Spring Boot microservices) + Python GenAI pipelines
• Build document AI workflows:
• ingestion OCR extraction embeddings indexing retrieval response with citations
• Implement LLM evaluation + observability:
• hallucination detection, quality scoring, groundedness checks
• Integrate model safety and governance:
• guardrails, policy filtering, PII redaction, secure tool usage
• Deploy scalable solutions on cloud with CI/CD, monitoring and performance tuning

Preferred / Emerging Tech Stack (Strong Plus)

These are high priority for the Emerging Tech client:

Agentic AI / Orchestration

• LangGraph, tool calling, function calling, autonomous workflows
• Multi-agent collaboration patterns (planner-executor, reflection loops, memory)

LLMOps & Evaluation

• LangSmith, TruLens, RAGAS, DeepEval, Phoenix Arize, prompt versioning
• model behavior testing, regression testing, prompt scoring

Vector / Search

• FAISS / Pinecone / Weaviate / Milvus / OpenSearch vector engine
• Hybrid search + reranking (cross-encoders)

Model & Training

• Hugging Face, PEFT / LoRA fine-tuning
• PyTorch, transformers

Governance

• Guardrails, prompt injection defense, PII filtering
• secure retrieval systems, audit trails and citations

Required Skills

Programming & Backend

• Strong hands-on experience in:
• Java (must-have)
• Spring Boot / Microservices / REST APIs
• Strong experience in:
• Python (must-have) for LLM pipelines and experimentation

GenAI (Must Have)

• Recent hands-on experience with:
• Prompt Engineering (production use)
• RAG pipelines
• Embeddings + vector search
• hallucination mitigation + grounding/citation strategies
• Experience with GenAI frameworks:
• LangChain / LlamaIndex
• LangGraph / Agent frameworks

Cloud & AI Platform

• Experience with one or more:
• AWS Bedrock / SageMaker
• OpenSearch vector/hybrid search
• Lambda / ECS / ECR
• Experience with document AI services:

Textract / OCR pipelines

We are an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, veteran status, or any other protected status.