SCRY AI is an innovative AI-driven technology company focused on building intelligent, scalable, and high-performance solutions. We work with modern technologies across Software Engineering, AI/ML, and Data to solve real-world business problems and deliver impactful digital products. We are seeking a skilled Forward Deployed AI/ML Software Engineer with strong hands-on experience in Generative AI, RAG, LLMs, backend engineering, and Voice AI. The candidate should combine strong software engineering skills with practical AI/ML expertise and be comfortable working directly with customers to build, integrate, deploy, troubleshoot, and optimize production AI solutions across varied environments.
Key Responsibilities
- Design, develop, and deploy scalable GenAI and RAG applications using LLMs such as OpenAI, Claude, Llama, Qwen, and other open-source models.
- Build complete RAG pipelines including document ingestion, chunking, embeddings, vector databases, retrieval, reranking, prompt engineering, and response generation.
- Develop and integrate Voice Bot / Conversational AI solutions connecting ASR, LLM/SLM, TTS, telephony, APIs, and business workflows.
- Build robust Python backend services and APIs using frameworks such as FastAPI/Flask.
- Develop Agentic AI and workflow automation solutions using frameworks such as LangChain/LlamaIndex, including tool calling and external system integrations.
- Integrate AI applications with SQL/NoSQL databases, APIs, enterprise systems, and customer-specific data sources.
- Work directly with customers and stakeholders to understand requirements, troubleshoot issues, demonstrate solutions, and translate business needs into technical implementations.
- Take AI/ML solutions from POC to production, focusing on scalability, reliability, latency, monitoring, and maintainability.
- Deploy and troubleshoot AI applications using Docker across cloud, on-premises, and customer environments.
- Optimize AI applications for latency, throughput, cost, model performance, and resource utilization.
- Follow strong software engineering practices including Git, CI/CD, testing, logging, monitoring, code reviews, and documentation.
- Collaborate with Data Scientists, ML Engineers, Product, Infrastructure, and customer teams to deliver and support production-ready AI solutions.
Key Qualifications
- 3+ years of experience in Software Engineering, AI/ML Engineering, Data Science, or GenAI, with strong hands-on development experience.
- Strong proficiency in Python, backend development, and software engineering fundamentals.
- Strong hands-on experience building and deploying RAG-based applications and LLM solutions.
- Experience with LangChain, LlamaIndex, Hugging Face, vector databases, embeddings, reranking, or equivalent technologies.
- Good understanding of LLMs, prompt engineering, Agentic AI, tool calling, MCP, and workflow automation.
- Experience with Voice AI / Voice Bots, preferably including ASR, TTS, telephony, and real-time conversational pipelines.
- Experience with PostgreSQL/SQL, MongoDB, Redis, or similar databases, along with REST APIs and backend integrations.
- Strong experience with FastAPI/Flask, microservices, Docker, and backend architecture; Kubernetes is a plus.
- Experience with AWS/Azure/GCP and cloud or on-premises deployments.
- Knowledge of CI/CD, automated testing, Git, logging, monitoring, production debugging, and AI/ML inference optimization.
- Strong problem-solving, communication, customer-facing, and collaboration skills, with the ability to work independently in fast-paced environments.
Good to Have
- Experience with Kubernetes, cloud-native architectures, CI/CD, and production observability.
- Exposure to MCP, Agentic AI frameworks, AI evaluation, model optimization, and LLMOps/MLOps.
- Experience working with customer deployments, POCs, enterprise integrations, and troubleshooting in cloud/on-premises environments.
