AI ML Engineer (7+ Years)

InApp is seeking a Senior Python Developer who excels at building scalable, AI-integrated systems using modern tools and frameworks. The ideal candidate will integrate AI models into backend systems, develop cloud-native applications, and collaborate with cross-functional teams to enhance productivity and innovation in AI development.

Responsibilities:

• Integrate APIs from multiple AI platforms (OpenAI, Anthropic, Gemini, Llama, Mistral, etc.) into scalable backend systems
• Build multi-model orchestration layers balancing cost, latency, and accuracy
• Fine-tune prompts, manage context windows, and implement RAG (Retrieval-Augmented Generation) solutions for domain-specific use cases
• Optimize token usage, caching, and filtering strategies to enhance system efficiency and user experience
• Design and implement AI-enabled workflows seamlessly integrated with web, mobile, or enterprise ecosystems
• Develop Python-based backends and APIs using frameworks like FastAPI, Flask, or Django
• Build and deploy microservices and cloud-native services leveraging Docker, Kubernetes, and serverless architectures
• Collaborate with frontend, DevOps, and product teams to ensure smooth feature delivery and deployment
• Monitor and evaluate AI responses through metrics, evaluation frameworks, or RLHF-inspired feedback loops
• Implement AI guardrails for responsible usage including bias detection, toxicity filtering, and compliance enforcement
• Debug and resolve performance or reliability issues in AI-powered production systems
• Stay up to date with the evolving AI model landscape, exploring new models, APIs, and orchestration frameworks
• Experiment with multi-modal AI (vision, text, speech) for applicability in client scenarios
• Work closely with cross-functional teams to translate business goals into intelligent, automated features

Requirements:

• Expert in Python backend development with hands-on experience integrating AI models, building cloud-native microservices, and using AI-assisted coding tools for faster, smarter development
• Proven hands-on experience integrating LLM APIs (OpenAI, Claude, Gemini, Llama, etc.)
• Strong expertise in AI/ML frameworks (TensorFlow, PyTorch, scikit-learn, Hugging Face, etc.) as essential qualification
• Practical knowledge of LangChain, LlamaIndex, Codium or similar frameworks for AI workflow orchestration
• Understanding of prompt engineering, embeddings, vector databases (Pinecone, Weaviate, FAISS, pgvector), and RAG pipelines
• Strong background in cloud platforms (AWS, GCP, Azure), containerization, and orchestration
• Deep understanding of REST/GraphQL APIs, async programming, task queues, and caching mechanisms
• Familiarity with SQL/NoSQL databases (PostgreSQL, MongoDB, Redis)
• Experience using AI-assisted tools such as GitHub Copilot, ChatGPT API, AutoGen, or OpenDevin for coding and testing automation
• Exposure to CI/CD pipelines and Infrastructure as Code (Terraform, Pulumi)
• Knowledge of data preprocessing, NLP/NLU, and model evaluation techniques
• Data Engineering & Processing, Data pipeline development, ETL/ELT processes, Batch processing and stream processing frameworks, Large-scale data handling with pandas, NumPy, Dask
• Hands-on with multi-modal AI (vision, text-to-speech, speech-to-text)
• Experience with MLOps practices including CI/CD for AI pipelines, model monitoring, and drift detection
• Background in fine-tuning, reinforcement learning, or custom model training
• Familiarity with enterprise security standards (GDPR, HIPAA, SOC2)
• Contributions to open-source or personal AI-assisted coding initiatives