Generative AI Engineer

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.What You'll Be Working OnArchitecting and developing end-to-end Generative AI applications and enterprise-grade AI product capabilities.Building advanced RAG pipelines involving document ingestion, parsing, chunking, embeddings, semantic search, hybrid retrieval, reranking, and response generation.Designing and implementing AI Agents, multi-agent systems, tool/function calling, and agentic workflows.Developing intelligent applications using LLMs, Prompt Engineering, Context Engineering, and workflow orchestration.Building scalable Python backend services and REST APIs using FastAPI, Flask, or equivalent frameworks.Integrating LLMs with databases, vector stores, internal services, and enterprise systems.Implementing LLM evaluation, response validation, hallucination mitigation, and retrieval quality measurement.Taking complete ownership of application development, deployment, monitoring, and production support.Optimizing AI solutions for accuracy, scalability, performance, latency, security, and cost efficiency.What We're Looking ForStrong Software Engineering Fundamentals2+ years of relevant professional experience.Excellent hands-on proficiency in Python.Strong understanding of Data Structures, Algorithms, OOP, Design Patterns, and System Design.Experience independently developing complete applications and backend services.Strong debugging, problem-solving, coding, and software architecture skills.Generative AI & LLM ExpertisePractical experience building real-world LLM-powered applications.Strong hands-on experience with RAG architectures and retrieval pipelines.Experience developing AI Agents and agentic workflows.Understanding of Prompt Engineering, Context Engineering, tool calling, and orchestration.Experience with LangChain, LangGraph, LlamaIndex, or equivalent frameworks.Retrieval & Data TechnologiesExperience with embeddings, vector databases, semantic search, and retrieval optimization.Familiarity with FAISS, Pinecone, Qdrant, Weaviate, Milvus, or Azure AI Search.Experience with structured and unstructured data processing.Understanding of document parsing, chunking, metadata filtering, and reranking.Backend & Production EngineeringExperience with FastAPI, Flask, or equivalent Python frameworks.Working knowledge of PostgreSQL, MongoDB, Redis, or similar databases.Experience with Docker, REST APIs, and application deployment.Exposure to AWS/Azure, CI/CD, MLOps, and application monitoring.What Will Make You Stand Out?We are particularly keen on candidates who:Have graduated from reputed engineering institutions with strong academic and computer science fundamentals.Have independently built applications or products from scratch rather than contributing only to isolated modules.Can demonstrate end-to-end ownership, from architecture and coding to deployment and production maintenance.Have built sophisticated RAG applications and AI agents beyond basic chatbot implementations.Understand the engineering behind AI frameworks rather than simply knowing how to use them.Have experience building enterprise AI, FinTech, RegTech, RiskTech, AML, or compliance-related applications.Have strong open-source contributions or technically challenging independent projects.We are looking for someone who can take an ambiguous problem, independently design the architecture, write production-quality code, build the complete application, and deliver a reliable solution with minimal supervision.