AI Engineer – LLM and Agentic AI
Bengaluru, Karnataka, India · Full Time
Be the first to apply
- Experience
- 3+ yrs
- Salary
- INR 6,000,000 – INR 6,000,000 / year
- Openings
- 1
- Posted
- 1 week ago
- Work mode
- In office
- Resume
- Required to apply
Where you'll work
Sign in to tell us what does and doesn't work for you here — it sharpens every match we show you.
Job description
About the Role
We are a rapidly expanding AI-focused LegalTech startup based in Bangalore seeking an AI Engineer to develop and deploy highly scalable, production-standard AI capabilities. You will be instrumental in building foundational infrastructure and ensuring the robustness of AI systems for practical use.
Key Responsibilities
- Develop evaluation frameworks, model harnesses, regression testing suites, and benchmarking infrastructures for large language models (LLMs).
- Lead the end-to-end production development of AI-powered features driven by LLMs, progressing from prototypes to large scale deployment.
- Create retrieval-augmented generation (RAG) pipelines, agentic workflows, tool integration systems, and orchestration layers.
- Design sophisticated prompts, context management strategies, and AI system architectures to maximize performance.
- Integrate, assess, and optimize both proprietary and open-source foundational AI models.
- Assume full ownership of AI production systems, including implementation of monitoring, guardrails, fallback mechanisms, and observability tools.
- Collaborate closely with cross-functional teams comprising product managers, engineers, and domain specialists to address complex process challenges.
Candidate Profile and Requirements
- A minimum of three years experience developing production-grade AI and LLM-based applications.
- Proven expertise in working with LLMs, retrieval-augmented generation, and agentic AI systems involving tool use.
- Experience designing and implementing AI evaluation frameworks, testing suites, benchmarks, and model harnesses.
- Strong software engineering skills, particularly with Python and backend development.
- Practical experience in prompt engineering and orchestration of LLM pipelines.
- Comprehensive understanding of both API-driven and open-source model capabilities, including trade-offs in model selection.
- Demonstrated ownership mindset with the ability to deliver quickly and operate independently.
Ideal Candidate
We are looking for an AI engineer who not only specializes in prompt engineering but also possesses the end-to-end ability to build supporting infrastructure, ship AI-powered features, rigorously evaluate these systems, and maintain them reliably in production environments.