AI / GenAI Solutions Engineer

This is a fully remote position, open to applicants in Pakistan.

📋 Description

• Design and implement production GenAI systems across various domains, such as conversational agents, automated workflows for orders and disputes, personalized discovery and recommendations, content generation, search relevance, and innovative use cases.

• Take ownership of features from start to finish, including problem framing, model selection, backend services (FastAPI, Python), frontend integration (React, TypeScript), evaluation, deployment, and monitoring.

• Create agentic workflows that incorporate tool calling, multi-step reasoning, retrieval augmented generation, and integrations with internal APIs, third-party SaaS, and event-driven systems.

• Develop the retrieval and embeddings architecture, involving chunking strategies, embedding model selection, vector indexes, hybrid search, reranking, and retrieval evaluation pipelines.

• Ensure reliability and cost-effectiveness through streaming, prompt caching, latency management, token cost optimization, observability for LLM calls, and effective fallback mechanisms for model or upstream failures.

• Implement rigorous evaluation processes through offline and online evaluations, focusing on response quality, tool call accuracy, hallucination rates, retrieval precision, and business KPIs.

• Foster innovation and research by assessing new models, frameworks, and agent patterns, conducting targeted experiments, and integrating successful strategies into production.

• Guide and elevate the capabilities of engineers within the team on AI and ML best practices, prompt engineering, and readiness for production.

• Collaborate cross-functionally with Product, Engineering, Data, Ops, and CX teams to pinpoint high-impact AI opportunities and successfully deliver them.

⛳️ Requirements

• A minimum of 5 years of experience in building production software, including at least 2 years in deploying LLM and ML-powered features at scale.

• Proficient in Python for backend services, scripting, data pipelines, and ML tools.

• Practical knowledge in TypeScript and React for the direct integration of AI features into product interfaces.

• Hands-on experience with major LLM providers (Gemini, Claude, GPT), including tool and function calling, structured outputs, streaming, prompt caching, and cost management.

• In-depth knowledge of Retrieval Augmented Generation (RAG), encompassing document ingestion, chunking, embedding generation, vector databases (pgvector, Pinecone, Weaviate, or similar), hybrid retrieval, and reranking.

• Solid understanding of embeddings and vector search principles: dense vs. sparse representations, similarity metrics, indexing strategies (HNSW, IVF), and dimensionality trade-offs.

• Strong foundation in ML and NLP concepts: transformer architectures, tokenization, fine-tuning vs. prompting trade-offs, classification, ranking, and evaluation methodologies.

• Experience with scripting and automation for data preparation, model evaluation frameworks, and offline analysis.

• Familiarity with relational databases (PostgreSQL), caching solutions (Redis), REST, SSE, WebSockets, and event-driven architectures.

• Proven experience with observability, A/B testing, and safely rolling out model updates.

🏝️ Benefits

• Opportunity to work on cutting-edge AI technologies and innovative projects.

• Collaborative and dynamic work environment with cross-functional teams.

• Professional development and mentorship opportunities.

• Competitive compensation and benefits package.