Senior Gen AI Engineer

Working Hours : Full Time

Locations : Hyderabad

Experience : 6 –10 years

apply now

apply now
About the Role:

Soothsayer Analytics is a global AI and Data Science consultancy headquartered in Detroit, with a thriving delivery center in Hyderabad. We design and deploy end-to-end custom Machine Learning solutions spanning predictive analytics, optimization, NLP, and GenAI that help leading enterprises forecast, automate, and gain a competitive edge. Join us to tackle high-impact, cross-industry projects where your ideas move rapidly from concept to production, shaping the future of data-driven decision-making.

Job Overview

We are seeking a skilled Senior Gen AI Engineer with strong ML fundamentals and data engineering expertise to lead the development of scalable AI/LLM solutions. This role focuses on integrating AI models into production, optimizing machine learning workflows, and creating scalable AI-driven systems. The ideal candidate will have strong experience with Machine Learning Engineering, model evaluation techniques, feedback loop creation, and integrating advanced technologies such as Large Language Models (LLMs). The AI Engineer will also work on designing and implementing AI orchestration pipelines, with a special emphasis on prompt engineering, vector databases, and embedding strategies for efficient data handling and processing. You will design, fine-tune, and deploy models (e.g., LLMs, RAG architectures) while ensuring robust data pipelines and MLOps practices.

Key Responsibilities

Machine Learning Engineering:

·         Develop, train, and deploy ML models, ensuring they are optimized for production environments.

·         Create and maintain automated feedback loops to enhance model accuracy and performance.

·         Implement ML pipelines for continuous evaluation and refinement of models in production.

AI/LLM Development & Orchestration:

·         Fine-tune and optimize LLMs (e.g., GPT, Llama) and traditional ML models for production.

·         Implement retrieval-augmented generation (RAG), vector databases, and orchestration tools (e.g., LangChain).

·         Integrate Large Language Models (LLMs) into business applications.

·         Build AI orchestration systems to manage the end-to-end lifecycle of AI models, including deployment and scaling, utilizing frameworks like LangGraph.

·         Design and implement AI agents with effective Chains and Tools for complex task automation and problem-solving, enabling agents to perceive, reason, act, and adapt autonomously.

·         Work with Vector Databases (e.g., Pinecone, Weaviate etc) to store and query high-dimensional data for AI applications.

·         Implement Agent-to-Agent (A2A) communication and Model Connect Protocol (MCP) for seamless interaction and collaboration within complex multi-agent AI systems.

Model Evaluation & Feedback Loops:

·         Set up evaluation metrics and processes to assess model performance over time.

·         Create feedback loops using real-world data to improve model reliability and accuracy.

Text-to-SQL & Generative AI-driven Solutions:

·         Develop GenAI-driven Text-to-SQL solutions to automate database queries based on natural language input.

·         Optimize GenAI workflows for database interactions and information retrieval.

Embedding/Chunking & Prompt Engineering:

·         Design and implement embedding and chunking strategies for scalable data processing.

·         Utilize Prompt Engineering techniques to fine-tune the performance of AI models in production environments, guiding agent behavior, providing context, and structuring output.

Data Engineering:

·         Build scalable data pipelines for unstructured/text data.

·         Optimize storage/retrieval for embeddings (e.g.,  Pinecone).

MLOps/LLMOps & Deployment:

·         Containerize models (Docker) and deploy on cloud (AWS/Azure/GCP) using Kubernetes.

·         Design CI/CD pipelines for LLM workflows (experiment tracking, monitoring), leveraging GitHub for version control and collaboration.

·         Work with DevOps to optimize latency/cost trade-offs for LLM APIs.

·         Implement robust Security measures for AI/LLM solutions throughout the development and deployment lifecycle, addressing data protection, privacy, manipulation risks (e.g., prompt injection), system integrity, and access control.

Collaboration:

·         Mentor junior team members on ML engineering best practices.

Required Skills & Qualifications

Education: BS/ MS/ PhD in CS/AI/Data Science (or equivalent experience).

Experience: 6+ years in ML + data engineering, with 2+ years in LLM/GenAI projects.

Skills Matrix

Candidates must submit a detailed resume and fill out the following matrix:

Skill

Details

Skills Last Used

Experience (months)

Self-Rating (0–10)

Python

 

 

 

 

ML Engineering

 

 

 

 

SQL/NoSQL

 

 

 

 

Apache Spark/Kafka

 

 

 

 

LLM Frameworks (LangChain, LangGraph)

 

 

 

 

MLOps/LLMOps (Docker/K8s, CI/CD, Experiment Tracking, Monitoring)

 

 

 

 

Cloud (AWS/Azure/GCP)

 

 

 

 

Vector Databases (Pinecone, Weaviate)

 

 

 

 

Prompt Engineering

 

 

 

 

AI Agent Design (Chains, Tools)

 

 

 

 

A2A / MCP

 

 

 

 

GitHub

 

 

 

 

Security (AI/LLM)

 

 

 

 

Instructions for Candidates:

·         Provide a detailed resume highlighting projects related to LLMs, data engineering, MLOps, GenAI applications, and CI/CD with GitHub.

·         Fill out the matrix above with accurate dates, experience duration, and self-ratings.

 

Apply for this job