AI Software Engineer

AI Software Engineer

Locations: Bangalore / Remote (Anywhere in India)

About EnCharge AI: EnCharge AI is dedicated to building the future of AI platforms. Our innovative in-memory computing architecture provides a substantial leap in compute energy efficiency and performance for AI inference workloads, addressing the evolving demands of artificial intelligence. We are an accomplished team of AI researchers, silicon and systems engineers, and architects, supported by prominent investors, aiming to become the essential platform for the next era of AI innovation.

The Opportunity: Video generation, a highly compute-intensive and promising area of AI, stands to benefit immensely from our hardware's energy efficiency. We are developing a comprehensive video generation stack designed to highlight the transformative capabilities of our silicon while providing immediate value to customers. As a Software Engineer, you will be instrumental in constructing the infrastructure and applications that will bring our video generation capabilities to market. Your responsibilities will include developing the serving stack, customer-facing APIs, and agentic systems that showcase the synergy between video generation and energy-efficient hardware. This is a foundational position where you will architect production systems from the ground up, make crucial technical decisions, and build software that directly supports our go-to-market strategy.

Key Responsibilities:

• Inference & Serving Infrastructure: Design and implement scalable serving infrastructure for video generation models (e.g., Wan, LTX-Video, Flux), prioritizing optimization for latency, throughput, reliability, and cost.
• API & Platform Development: Create robust APIs and SDKs for seamless integration of video generation into customer and partner products, designing flexible yet user-friendly abstractions.
• Video Applications & Demos: Develop engaging demo applications that effectively showcase our platform's capabilities, including interactive experiences, batch processing, and industry-specific solutions to support the go-to-market team.
• Agentic Workflows: Build agentic systems that leverage video generation as a core component, such as autonomous video editing pipelines, multi-step generation processes, and tool-use frameworks to expand the possibilities of video AI.
• Production Operations: Establish comprehensive monitoring, observability, and deployment practices for video generation workloads, ensuring system reliability, debuggability, and readiness for customer deployment.

Qualifications:

• 5+ years of software engineering experience, with a strong focus on backend systems or ML infrastructure.
• Proficient in Python and at least one systems programming language (Go, Rust, C++).
• Proven experience in building and operating production APIs and serving systems.
• Familiarity with ML inference pipelines, including model serving, GPU workloads, and batching strategies.
• Adaptable and comfortable working in fast-paced, ambiguous environments where you can define the roadmap.
• Strong product acumen, with an understanding of how software will be utilized.

Nice to Have:

• Experience with video processing pipelines or media infrastructure.
• Background in building agentic systems or multi-step AI workflows.
• Familiarity with diffusion models or generative AI systems.
• Experience with orchestration frameworks like Kubernetes or Ray.
• A track record of shipping developer tools or APIs.

Contact: Uday Mulya Technologies, muday_bhaskar@yahoo.com