Job Title

Manager – GenAI Engineering

Role Overview

We are seeking a GenAI Engineering Manager with 8+ years of experience to lead the design, development, and governance of enterprise-scale GenAI solutions. The role requires deep hands-on expertise in Python, RAG architectures, agentic AI frameworks, prompt evaluation, and LLM platform strategy, along with strong people and technical leadership skills.

You will be responsible for defining GenAI architecture standards, mentoring engineers, ensuring production readiness, and driving best practices across prompt engineering, evaluation, security, and deployment.

Key Responsibilities

• Own end‑to‑end architecture, design decisions, and technical governance for enterprise‑scale GenAI solutions, ensuring solutions are secure, scalable, reliable, and aligned with business objectives.
• Lead the design and implementation of advanced RAG architectures, covering chunking strategies (semantic, hierarchical, hybrid), retrieval optimization, reranking, metadata filtering, and grounding assurance.
• Define and standardize prompt engineering best practices across teams, including system prompt design, instruction tuning, reasoning control, and alignment with use‑case objectives.
• Establish and drive prompt evaluation frameworks, covering qualitative and quantitative evaluation of accuracy, relevance, hallucination rate, determinism, cost efficiency, latency, and prompt regression risks.
• Guide teams on effective use of Chain‑of‑Thought (CoT) and alternative reasoning strategies while balancing explainability, cost, and security concerns.
• Lead adoption and production usage of agentic AI frameworks such as LangChain and LangGraph, including multi‑agent coordination, tool calling, memory management, routing, and fallback strategies.
• Decide when to use agentic workflows vs deterministic pipelines, based on complexity, reliability, observability, and enterprise risk tolerance.
• Oversee design and development of FastAPI‑based GenAI services, ensuring robust API design, validation, versioning, performance optimization, and backward compatibility.
• Define and enforce authentication and authorization standards, including secure JWT‑based access control for GenAI services and integrations.
• Lead cloud architecture and deployment strategy on AWS, including environment setup, CI/CD practices, infrastructure scalability, and operational readiness.
• Guide teams on effective use of DynamoDB, including data modeling, access patterns, performance tuning, and cost optimization for GenAI workloads.
• Define organization‑wide strategy for vector databases, embedding models, embedding lifecycle management, similarity tuning, and retrieval performance optimization.
• Own LLM platform strategy, including evaluation and usage of AWS Bedrock and Azure OpenAI, model selection, version upgrades, cost trade‑offs, and compliance considerations.
• Establish guardrails and safety mechanisms for GenAI systems to control hallucinations, enforce grounding, prevent data leakage, and ensure responsible AI usage.
• Drive observability best practices, including logging, monitoring, tracing, and evaluation signals for GenAI pipelines, prompts, and agent behaviors.
• Mentor, coach, and technically guide GenAI engineers through code reviews, design reviews, architecture discussions, and best‑practice sharing.
• Collaborate closely with product, business, and stakeholders to translate business problems into scalable, production‑ready GenAI architectures and delivery plans.
• Ensure GenAI solutions mature from PoC to production, with a strong focus on reliability, maintainability, cost control, and enterprise readiness.

Mandatory Skills

• 8+ years of experience in software or AI engineering
• Strong expertise in Python Object-Oriented Programming
• Deep hands-on experience with RAG pipelines, chunking, guardrails, and CoT
• Advanced Prompt Engineering with structured evaluation techniques
• Strong experience with Agentic AI using LangChain and LangGraph
• Expertise in FastAPI and large-scale API integrations
• Strong AWS experience, including DynamoDB
• Secure API design with JWT authentication
• Strong knowledge of vector databases and embedding optimization
• Hands-on with AWS Bedrock and Azure OpenAI

Good to Have

• Working knowledge of LLMOps / MLOps frameworks
• Experience with prompt evaluation frameworks, logging, and monitoring
• Exposure to enterprise chatbots, copilots, or analytics-driven GenAI platforms
• Experience building systems under compliance or regulated environments

What we are looking for

• Strong problem-solving and system design skills
• Ability to convert business problems into GenAI architectures
• Experience building production-ready AI solutions
• Ownership mindset and attention to quality and reliability
• Clear communication and documentation skills