Gen AI Engineer Lead Architect - Agentic AI & AWS

Hi Everyone!! Greeting from Intuition IT – Intuitive Technology Recruitment!!!!

We have an existing job opportunity with our leading Client

If you are interested with above Job Description, please share your CV to this email id : Maheshwari.p@Intuition-IT.com

Please go through Below details with Job Description

Area of Expertise

Job title:::Gen AI Engineer Lead Architect – Agentic AI & AWS Type:-Long term Contract Location: Remote in India Immediate to 15 days Exp : 4 to 10 years

AI Engineer We are looking for an

Agentic GenAI Engineer

to design, build, and deploy

autonomous, goal‑driven AI agents

powered by Large Language Models (LLMs) and multimodal foundation models. This role focuses on creating

self‑directing, tool‑using, and decision‑making AI systems

that can plan, reason, act, and learn while integrating deeply with enterprise data and applications.

Key Responsibilities Agent & Model Development Design and implement

agentic AI systems

capable of planning, reasoning, tool usage, memory management, and autonomous execution. Implement agents in

LangGraph

(state machines, multi-agent flows, tool calling, memory patterns). Build

RAG pipelines

: chunking, embedding strategies, retrieval, reranking, citation grounding. Integrate with models (Claude/Gemini/ChatGPT via approved gateways) and

AWS Bedrock

. Implement tool adapters and interoperability using

MCP protocol

(as applicable). Build evaluation harness: unit tests + LLM evals, regression suites, synthetic test generation. Optimize latency and cost (caching, batching, streaming responses, prompt compression).Implement

prompt strategies, system prompts, agent policies, and guardrails

to ensure safe, reliable, and goal‑aligned agent behavior. Build and manage

single‑agent and multi‑agent architectures

for task decomposition, collaboration, and consensus. Data, Memory & Knowledge Integration Collect, preprocess, and curate structured and unstructured data for training, evaluation, and agent knowledge grounding. Implement

retrieval‑augmented generation (RAG)

using embeddings, chunking strategies, and vector search. Design

agent memory systems

(short‑term, long‑term, episodic, and semantic memory) for context persistence and learning. Generate and manage

synthetic data

to improve reasoning, planning, and decision‑making capabilities. AI Pipelines & Orchestration Build and maintain

end‑to‑end agent pipelines

, from perception and planning to action execution and feedback loops. Develop backend services and APIs using

Python and/or .NET

to orchestrate agents, tools, and workflows. Integrate external tools, APIs, databases, and enterprise systems to enable

tool‑calling and action execution

by agents. Implement evaluation frameworks to measure

agent effectiveness, autonomy, latency, and reliability

. Cloud, Deployment & MLOps Deploy and scale agentic AI solutions on

Azure, AWS, or GCP

. Integrate

Bedrock Agent Core,

Azure Cognitive Services or equivalent platform services

to extend agent capabilities. Use

Docker and Kubernetes

to deploy, manage, and scale autonomous AI systems. Ensure robustness, observability, security, and cost‑efficiency of agentic solutions in production.

Required Skills & Experience Core Technical Skills Strong foundation in

computer science, machine learning, and deep learning

. Hands‑on experience with

Generative AI and LLMs

, including Transformers, GANs, and VAEs. Experience building or orchestrating

agentic frameworks

(e.g., planners, tool‑calling, memory, multi‑agent coordination). Proficiency in

Python

and experience with

PyTorch, TensorFlow, or Keras

. Solid understanding of

NLP

, embeddings, semantic search, and contextual reasoning. Data, MLOps & Systems Experience with

data preprocessing, augmentation, labeling, and synthetic data generation

. Experience deploying

AI/agent systems in production

with monitoring and feedback loops. Familiarity with

MLOps and AgentOps

practices (model/version management, prompt/version control, evaluation). Cloud & Infrastructure Experience with

Azure, AWS, or GCP

for AI workloads. Strong understanding of

Docker and Kubernetes

for scalable deployments. Exposure to

vector databases

and search platforms.

Gen AI Lead – Agentic AI & AWS Role Summary We are seeking a

hands-on senior engineer

responsible for designing, building, and optimizing Agentic AI systems. This role leads by technical depth and implementation, owning complex agent workflows, RAG strategies, context engineering, and production-grade LLM services. The role may mentor other engineers and influence architecture but remains deeply involved in coding and problem-solving.

Key Responsibilities Design and implement

agent-based workflows using LangGraph

, including: Planning and execution agents Tool-using agents Multi-step and multi-agent orchestration Stateful agents with memory and checkpoints Build

production-grade RAG pipelines

: Chunking and metadata strategies Hybrid retrieval (keyword + vector) Re-ranking and citation grounding Context window optimization Implement

context engineering strategies

: Dynamic prompt assembly Tool-aware context routing Conversation state compression and summarization Own

prompt engineering standards

: Prompt templates, versioning, evaluation, and rollback strategies Structured outputs (JSON / schema-based responses)Collaboration & Delivery Collaborate with

product managers, data scientists, and engineering teams

to translate business requirements into technical solutions. Provide technical leadership across multiple initiatives and engage with senior stakeholders on solution strategy. Ensure adoption of

responsible AI

, ethical AI principles, and model governance. Backend & API Development

Develop scalable **Python services using FastAPI** for: Agent invocation Tool execution Retrieval services Feedback and evaluation endpoints Implement streaming responses (SSE/WebSockets) and async execution patterns. Handle retries, fallbacks, timeout handling, and partial-failure recovery for agents.

Model & Platform Integration

Integrate and optimize usage of

AWS Bedrock models

(Claude, etc.). Integrate and optimize usage of

AWS Agent Core Platform or other similar platforms Implement

multi-model routing strategies

(Claude / Gemini / ChatGPT) based on task type, latency, or cost. Apply

guardrails and safety controls

at model and application level. Use

MCP protocol

for tool interoperability where applicable.

Evaluation, Quality & Reliability

Build LLM evaluation frameworks: Golden datasets Regression tests Automated scoring (relevance, groundedness, tool correctness) Actively reduce hallucinations through: Better retrieval Strong grounding Tool validation Analyze failures using logs, traces, and prompt diffs.

AI Lead

Required Skills & Experience Experience experience in software engineering or platform development. 3+ years of hands‑on experience in Generative AI / LLM‑based systems

. Proven ability to lead complex technical initiatives in enterprise environments. Technical Expertise Strong hands‑on experience with

AWS

, including: Deep hands-on experience with LangGraph Strong understanding of

Agentic AI patterns

: Tool calling Planning vs execution Memory management Determinism vs autonomy trade-offs Proven experience building

RAG systems in production

. Strong

prompt engineering and context engineering skills.Deep understanding of

LLMs, transformer architectures, RLHF

, and

agentic AI frameworks

such as: AutoGPT, LangGraph, LangChain, CrewAI Backend Engineering Expert-level Python. Strong experience with FastAPI (async, middleware, auth, testing). API design and performance tuning.

Cloud & Platform

Hands-on experience with AWS, especially: AWS Bedrock IAM basics CloudWatch logging/metrics Understanding of cost, latency, and throughput trade-offs in LLM systems. Experience with: Prompt engineering and fine‑tuning Model evaluation and optimization Vector databases (Pinecone, FAISS) Embeddings and RAG architectures Strong problem‑solving skills and ability to lead technically complex projects.