Agentic AI Engineer

EXL Service -
United States

Apply Now

Job Details

Full-time

Qualifications

AI models
Containerization systems
Software engineering
Continuous Delivery (CD) implementation
IT system monitoring
Generative models
System design
Public Cloud
AI platforms (beyond public GPTs)
Scalable systems
Computational framework
Enterprise software systems development
Databases
Microservices
System design for system development
Model deployment
Scalability
Production monitoring
Distributed computing
DevOps automation
API integrations
Machine learning libraries
Machine learning frameworks
Python
Design (software development lifecycle)
MLOps
Generative AI
Debugging
Production troubleshooting
System performance monitoring

Full Job Description

Job Description: We are seeking a Lead Agentic AI Engineer with a strong software engineering foundation to design, build, and scale autonomous and semi‑autonomous AI systems . This role goes beyond prompt engineering or isolated models—you will architect multi‑agent systems that plan, reason, call tools, interact with enterprise systems, and operate safely at scale.

You will work on agent orchestration, RAG pipelines, tool‑calling, memory, observability, and AgentOps , while ensuring production readiness, compliance, and reliability.

Responsibilities: Agentic AI System Design

Design and implement multi‑agent architectures including:
- Orchestrator / supervisor agents
- Task‑specialized agents (research, extraction, validation, decisioning)
- Reflection, critique, and self‑correction loops
Build goal‑driven agent workflows with constrained autonomy and human‑in‑the‑loop patterns.
Define agent boundaries, decision policies, and escalation logic.

LLM, RAG & Tooling

Build enterprise‑grade RAG systems :
- Ingestion, chunking, metadata enrichment
- Vector indexing and retrieval strategies
- Grounded generation and citation control
Implement tool‑calling agents that interact with:
- APIs, databases, search systems
- Internal platforms and workflows
Optimize latency, cost, and accuracy across LLM interactions.

Production Engineering & AgentOps

Build agentic systems as scalable backend services (FastAPI / REST / async services).
Apply strong software engineering discipline :
- Modular code, clean abstractions, testability
- CI/CD, versioning of prompts, tools, and agents
Implement AgentOps / LLMOps , including:
- Evaluation harnesses (prompt, retrieval, agent behavior)
- Observability (traces, metrics, decision paths)
- Rollback and controlled rollout strategies
Ensure robustness against hallucinations, loops, tool failures, and unsafe actions.

Governance, Safety & Reliability

Implement guardrails, policies, and monitoring for agent behavior.
Design systems with traceability, auditability, and explainability .
Ensure secure handling of sensitive data (PII/PHI where applicable).
Enforce responsible‑AI principles in autonomous systems.

Technical Leadership

Lead design reviews and mentor junior engineers.
Influence platform standards for agentic AI across teams.
Partner with product managers, architects, and domain SMEs to translate workflows into agent behavior.

Qualifications: Strong Software Engineering Background (Must Have)

8–10 years of experience with backend/software engineering
Expert in Python (primary) and API‑based services
Experience with distributed systems, microservices, async processing
Strong understanding of system design, scalability, and performance

Agentic AI & GenAI Expertise

Proven experience building agentic AI systems (not just chatbots)
Hands‑on with agent frameworks (e.g., LangChain / LangGraph / equivalent)
Strong understanding of:
- Tool‑calling, planning, reflection
- Memory, state, and long‑running agents
Experience working with LLMs (cloud and/or open‑source)

RAG & Data Engineering

Production experience with vector databases
Knowledge of embeddings, retrieval strategies, reranking
Comfortable with structured + unstructured enterprise data

Platform & Ops

Docker, CI/CD, cloud deployments (AWS / Azure / GCP)
Experience with monitoring, logging, and production debugging
Familiarity with MLflow or similar experiment tracking tools

Nice to Have

Experience in healthcare, insurance, or regulated domains
Exposure to AI governance, compliance, or risk frameworks
Built internal AI platforms or reusable accelerators
Prior experience tech‑leading enterprise AI initiatives

Apply Now

Job Seeker Tools

Employer Tools

Browse

Stay Connected