We are looking for an AI Agent Engineer who can design, build, and operate intelligent agent systems in production. This role requires strong coding expertise combined with deep practical experience in LLM-based systems, orchestration frameworks, and real-world deployment challenges.
You will work at the intersection of AI, backend systems, and product development, owning end-to-end agent workflows that deliver measurable business value.
Key Responsibilities
- Design, build, and maintain AI agents in production environments
- Own end-to-end orchestration, including:
- Prompt design and optimization
- Tool integrations and agent skills
- Workflow design and execution
- Memory and context management
- Routing across models/providers
- Monitoring, logging, and fallback strategies
- Develop robust prompting systems, including reusable prompt libraries and structured outputs
- Build and maintain evaluation frameworks:
- Define success metrics
- Create evaluation datasets
- Analyze failures and continuously improve agent quality
- Ship user-facing product features across backend, frontend, and AI layers
- Debug complex issues across:
- LLM outputs
- Agent workflows
- Tool integrations
- UI and system bottlenecks
- Optimize systems for latency, cost, reliability, and scalability
- Collaborate with product, design, and business teams to deliver impactful AI-driven experiences
Required Qualifications
- 1–5 years of hands-on coding experience in Python and/or JavaScript/TypeScript
- Proven ability to independently build, debug, and maintain production systems
- Strong experience with:
- LLMs and AI agents
- Tool usage and integrations
- Workflow/orchestration systems
- Prompt engineering and pipelines
- Deep understanding of agent reliability concepts:
- Prompt design
- Context and memory handling
- Structured outputs
- Tool calling
- Retries and fallbacks
- Guardrails and evaluation systems
- Experience building or using agent frameworks/tool abstractions in production
- Strong knowledge of:
- Multi-model orchestration
- Cost vs latency trade-offs
- Failure handling and observability
- Demonstrated ability to ship quickly and iterate based on real usage
- Strong product mindset with focus on delivering user value
- Proven track record of measurable impact, such as:
- Improved reliability
- Reduced latency/cost
- Increased user engagement or retention
Interested candidates Contact HR : 9944897564
Job Types: Full-time, Permanent
Pay: From ₹20,000.00 per month
Benefits:
- Health insurance
- Provident Fund
Experience:
- Python and or/ JavaScript/typescript: 2 years (Required)
Work Location: In person
