Job Description

We are seeking GenAI and Agentic AI Engineering Hands-on Lead or a Manager with a focus on delivery, client excellence and innovation. As an experienced Agentic AI Engineer with deep expertise in LLM, Azure AI, Snowflake, and Machine Learning ecosystems, you are responsible to design and implement enterprise-grade AI solutions. The ideal will have hands-on experience architecting end-to-end AI/ML systems—from data readiness pipeline through Agentic Solutions deployment— leveraging cloud-native architecture.

Test Driven Agentic AI Engineering, evaluation strategy, metric selection, ground-truth creation, and decisioning on model and prompting approaches. You’ll build and validate GenAI/agentic solutions, define what “good” means, and ensure solutions are measurably effective and safe before and after launch. You will build the GenAI solution in a production (model choice, RAG/agent behaviour, prompts, and evaluation).

Key Responsibilities:

- Translate business needs into testable GenAI and Agentic Engineering solutions, transparent outputs, and measurable success criteria; define scope boundaries (what the system should not attempt), including risks.
- Run feasibility assessments to choose the right approach: prompting vs RAG vs fine-tuning vs classical ML.
- Select and develop models based on task requirements (reasoning vs extraction vs classification) working with AI Engineering to understand latency/cost,



and risk profile.
- Design prompting strategies: instruction design, few-shot sets, structured outputs, tool/agent prompts, and robustness patterns. This will be implemented as an MVP and iterate based on eval results.
- Establish prompt iteration methodology driven by evals (not anecdotal testing): prompt versioning, ablations, and change control.
- Define the evaluation plan for GenAI systems and agentic workflows- designing and implementing evaluation from LLM as a judge and ensure evaluation includes fairness and bias considerations where applicable. Define acceptance thresholds and release gates tied to these metrics.
- Own experimentation and model improvements: Run structured experiments (across prompts, retrievers, chunking, models).
- Develop out methods for identifying model failures such as hallucination types, retrieval misses, instruction-following errors, formatting failures etc
- Provide recommendations for improvements grounded in evidence: what to change, expected lift, and trade-offs.
- Deliver an engineering-ready handoff: prompt packages and versioning approach, RAG configuration, tool schemas (if agentic), evaluation harness, datasets/ground truth, metric definitions, and go/no-go gates.
- Design scalable and secure Agentic AI architectures adhering to best practices in data engineering, MLOps and LLMOps.

📌 Lead / Manager - AI Engineering (Hyderabad)
🏢 Blend360
📍 Hyderabad