Prompt Engineer – AI Image & Video Generation (ON-SITE ONLY)

Job title and location Title : Prompt Engineer – AI Image & Video Generation

Location : Mumbai, India ( On‑site only , Immediate joiners preferred)

Employment : Full‑time

Role summary We are seeking an innovative AI Prompt Specialist to pioneer the integration of artificial intelligence in our creative production workflows. This role bridges creative storytelling with emerging AI technologies to accelerate content development while maintaining our signature quality standards.

Key responsibilities Design, test, automate and refine prompts for text‑to‑image and text‑to‑video tools (Midjourney, Sora, Veo 3, Kling, etc.) to achieve specific visual styles, narratives, and brand outcomes.

Generate high‑quality images and videos for ads, social content, product visuals, storyboards, and explainer content, ensuring outputs are commercially usable and on‑brand.

Systematically document prompt recipes, variants, and best practices to build an internal prompt library that others in the company can reuse.

Analyze results, troubleshoot issues (artifacts, inconsistencies, off‑brand results), and iteratively optimize prompts for quality, consistency, and speed of delivery.

Collaborate closely with creative, marketing, and product teams to translate briefs into clear prompt strategies and visual directions.

Stay on top of new features, models, and techniques in generative image and video tools and proactively bring them into the workflow.

Required skills and experience 1–3 years of hands‑on experience working with generative AI tools for images and / or video (e.g., Midjourney, Stable Diffusion, Runway, Pika, Sora, Veo 3, Kling, D‑ID, Synthesia or similar).

However, freshers with a graduation degree in Fine Arts, Animation, Visual Communication, Digital Media, Film Studies, or related creative fields are encouraged to apply.

Strong portfolio demonstrating AI‑generated images and / or videos, with clear indication of your role in prompt design and iteration.

Excellent written English; ability to write precise, descriptive prompts that control style, composition, lighting, camera angles, motion, and narrative.

Good understanding of visual storytelling, framing, basic cinematography concepts, and design principles (composition, color, typography).

Ability to work quickly under tight deadlines, run many experiments, and keep outputs organized and reproducible.

Nice‑to‑have Familiarity with multimodal AI workflows (text‑to‑video, text‑to‑image, image‑to‑image, text‑to‑audio).

Experience working with creative / marketing teams or in a content, advertising, or media environment.