Job description

About Us:

Solytics Partners is a global analytics firm recognized for innovation and excellence across Risk, Analytics, AI/ML, AML/FCC, and Fraud. We combine deep domain expertise with Artificial Intelligence, Machine Learning, Generative AI, and Large Language Models (LLMs) to build intelligent platforms and solutions for complex business and regulatory challenges.

Our products help organizations automate processes, improve decision-making, strengthen risk and compliance capabilities, and operate more efficiently in an evolving regulatory environment.

Job Overview:

We are looking for a hands-on Generative AI Engineer – Python with 2–6 years of experience to join our internal product engineering team.

The ideal candidate will have strong practical expertise in Python, Generative AI, LLMs, RAG, AI Agents, Prompt Engineering, and Vector Databases, combined with a strong software engineering mindset.

You will be responsible for designing, developing, deploying, and maintaining AI-powered product features end-to-end. This role requires the ability to independently own technical problems, make sound engineering decisions, and translate product requirements into scalable, reliable, and production-ready AI solutions.

Key Responsibilities:

Design and develop end-to-end Generative AI and LLM-powered applications using Python.
Own AI features across the development lifecycle, from requirements analysis and solution design through development, deployment, monitoring, and production support.
Build and optimize RAG pipelines, including document ingestion, parsing, chunking, embeddings, retrieval, reranking, context construction, and response generation.
Develop AI Agents and agentic workflows using LLMs, tool/function calling, workflow orchestration, and state or memory management.
Design effective Prompt Engineering and Context Engineering strategies to improve the accuracy, consistency, and reliability of LLM applications.
Implement semantic search and retrieval solutions using vector databases and embedding models.
Build robust pipelines for processing and transforming structured and unstructured data.
Develop scalable backend services and REST APIs using FastAPI, Flask, or similar Python frameworks.
Integrate LLMs with databases, internal services, APIs, enterprise systems, and third-party AI services.
Implement LLM evaluation and testing strategies, including quality metrics, test datasets, retrieval evaluation, response validation, and regression testing.
Implement appropriate logging, monitoring, observability, error handling, and fallback mechanisms for production AI systems.
Deploy and maintain AI applications using cloud platforms, Docker, CI/CD, and relevant MLOps practices.
Optimize AI applications for scalability, latency, reliability, and cost efficiency.
Troubleshoot production issues and continuously improve the quality and performance of AI features.
Apply relevant Machine Learning and Data Science concepts to solve product and business problems.
Collaborate with Product Managers, Data Scientists, ML Engineers, and Software Engineers to deliver AI-powered product capabilities.

Must-Have Skills:

Python & Software Engineering:

- 2–6 years of professional experience in software engineering, AI/ML engineering, or a closely related field.
- Strong hands-on experience with Python.
- Good understanding of OOP, data structures, exception handling, debugging, testing, and clean coding practices.
- Experience developing REST APIs and backend services.
- Strong problem-solving, analytical, and system-design skills.
- Ability to independently develop, debug, and maintain software components.

Generative AI & LLMs:

- Strong practical experience building applications using Generative AI and LLMs.
- Hands-on experience developing RAG-based applications.
- Practical experience implementing AI Agents or agentic workflows.
- Understanding of LLM tool/function calling and workflow orchestration.
- Strong understanding of Prompt Engineering and Context Engineering.
- Understanding of LLM challenges including hallucination, context limitations, latency, cost, and reliability.
- Experience with at least one LLM application framework such as LangChain, LangGraph, LlamaIndex, or an equivalent technology.

Retrieval & Data Processing:

- Hands-on experience with vector databases, embeddings, semantic search, and retrieval pipelines.
- Understanding of document processing, chunking strategies, metadata filtering, and retrieval optimization.
- Experience working with structured and unstructured data.
- Understanding of data preprocessing, transformation, and pipeline development

Production Engineering:

- Experience taking AI/ML applications from development or experimentation to deployable or production environments.
- Experience with Docker and containerized application development.
- Understanding of API integration, application deployment, logging, monitoring, and production debugging.
- Ability to evaluate trade-offs involving quality, latency, scalability, reliability, and cost.

Preferred Skills:

- Experience with AWS or Azure.
- Experience with FastAPI, Flask, or similar Python frameworks.
- Hands-on experience with LangChain, LangGraph, LlamaIndex, or equivalent frameworks.
- Experience with PostgreSQL, MongoDB, Redis, or similar databases.
- Experience with vector-search technologies such as FAISS, Azure AI Search, Pinecone, Qdrant, Weaviate, or Milvus.
- Exposure to LLM evaluation frameworks and techniques.
- Understanding of CI/CD, MLOps, and AI application observability.
- Exposure to MCP (Model Context Protocol) and enterprise tool integration.
- Familiarity with cloud-based AI services and scalable inference architectures.
- Exposure to traditional Machine Learning and Data Science workflows.

What We Are Looking For:

- Strong hands-on Python and software engineering capabilities.
- Practical experience building and integrating Generative AI applications.
- Ability to independently own technical problems and deliver reliable product features.
- Strong debugging, analytical thinking, and problem-solving skills.
- Ability to balance AI quality, performance, scalability, and cost.
- Curiosity and willingness to adopt emerging AI technologies while maintaining strong engineering practices.
- Strong communication and collaboration skills in a product-development environment.

Someone shared one job with you. ASAI keeps finding the rest.

Scored, not searched. Every role ranked against your actual profile.

Alerts as often as hourly. Reach new roles while the pile is still small.

Skill gaps, spelled out. See exactly which requirements you don't meet yet.

Verified jobs, only. Say no to ghost jobs. Your time deserves respect.