AI Agent Engineer - AI Consulting & Strategy

: Bachelor s/Master s degree

Work Location

: Chennai, India (Chennai/Remote/Hybrid)

Key Responsibilities :

• Build and maintain a

  centralized Agent Library

  for reusable components, prompts, and integration adapters.
• Develop

  agent frameworks and orchestration logic

  for multi-agent collaboration scenarios.
• Design

  integration connectors

  to institutional systems like ERP, SIS, CRM, or document repositories.
• Collaborate with LLM Engineers to improve agent reasoning, memory, and retrieval accuracy.
• Define

  agent governance frameworks

  , telemetry, and safety monitoring mechanisms.
• Implement

  agentic testing frameworks

  to ensure consistency, explainability, and reliability.
• Continuously benchmark and optimize agent workflows for latency, accuracy, and contextual relevance.

Required Technical Skills :

Agent Frameworks & Architecture

• Expertise in designing and implementing

  autonomous or semi-autonomous AI agents

  using frameworks like

  LangChain, AutoGen, CrewAI

  , or

  Semantic Kernel

  .
• Experience with

  multi-agent systems, memory management

  , and

  tool orchestration

  .
• Strong understanding of

  agent life cycle design

  , task delegation, and context management.

Reusable Agent Components

• Develop modular

  agent templates, skills

  , and

  toolkits

  that can be easily configured for multiple workflows.
• Build and maintain an

  enterprise Agent Library

  with metadata tagging, versioning, and documentation.
• Create reusable connectors for integrating agents with APIs, databases, and business systems.

Integration & Orchestration

• Design

  workflow orchestration patterns

  integrating agents with enterprise platforms (ERP, CRM, LMS, or HR systems).
• Implement

  event-driven architectures

  using message queues, APIs, or webhook triggers.
• Collaborate with DevOps/MLOps to enable

  continuous deployment

  and scaling of AI agents.

LLM & Context Management

• Integrate LLMs (OpenAI, Anthropic, Mistral, or local models) into agent reasoning pipelines.
• Manage

  context caching, vector retrieval, and memory stores

  for long-term agent context retention.
• Optimize

  prompt construction, chaining logic

  , and

  tool selection

  for efficient reasoning.

Governance, Security & Observability

• Implement

  guardrails, policy-based control

  , and

  access-level governance

  for enterprise AI agents.
• Set up

  agent telemetry and logging

  using observability tools (Prometheus, OpenTelemetry, Datadog, or Grafana).
• Ensure agents comply with

  data security, compliance, and auditability

  standards.

Programming & Infrastructure

• Strong development skills in

  Python, TypeScript

  , or

  Go

  , with emphasis on modular, testable design.
• Familiarity with

  containerization (Docker, Kubernetes)

  and

  cloud environments (AWS, Azure, GCP, or OCI)

  .
• Experience with

  API design, GraphQL

  , and

  asynchronous event-driven programming

  .

Required Skills & Experience :

• 5+ years of experience in

  AI/ML application development

  or

  enterprise integration engineering

  .
• Proven experience in

  agent framework development

  or

  LLM orchestration systems

  .
• Deep understanding of

  API-driven architectures, event streaming

  , and

  data integration

  .
• Hands-on experience with

  LangChain, AutoGen, CrewAI

  , or similar frameworks.
• Strong coding and automation skills with a focus on

  reusability and scalability

  .
• Experience in

  testing, evaluating, and deploying AI-driven workflows

  in enterprise environments.

Experience

: 5+ Years Experience

Education

: Bachelor s/Master s degree

Work Location

: Chennai, India (Chennai/Remote/Hybrid)

centralized Agent Library

for reusable components, prompts, and integration adapters.

agent frameworks and orchestration logic

for multi-agent collaboration scenarios.

integration connectors

to institutional systems like ERP, SIS, CRM, or document repositories.

agentic testing frameworks

to ensure consistency, explainability, and reliability.

autonomous or semi-autonomous AI agents

using frameworks like

toolkits

that can be easily configured for multiple workflows.

enterprise Agent Library

with metadata tagging, versioning, and documentation.

workflow orchestration patterns

integrating agents with enterprise platforms (ERP, CRM, LMS, or HR systems).

event-driven architectures

using message queues, APIs, or webhook triggers.

continuous deployment

and scaling of AI agents.

context caching, vector retrieval, and memory stores

for long-term agent context retention.

tool selection

for efficient reasoning.

access-level governance

for enterprise AI agents.

agent telemetry and logging

using observability tools (Prometheus, OpenTelemetry, Datadog, or Grafana).

data security, compliance, and auditability

standards.

containerization (Docker, Kubernetes)

and

AI/ML application development

or

agent framework development

or

testing, evaluating, and deploying AI-driven workflows